Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bul
    -0.75
     Rox
    -0.70
     Koz
    -0.68
    bul
    -0.66
     Mal
    -0.65
    </em>
    -0.65
    dal
    -0.63
    Bul
    -0.63
     Dal
    -0.63
    mapsto
    -0.62
    POSITIVE LOGITS
     Agree
    1.77
     agrees
    1.63
     Agre
    1.59
     Disagree
    1.57
    agree
    1.52
     agree
    1.51
    Agre
    1.48
     Agreed
    1.47
    Agree
    1.47
     Agreements
    1.44
    Act Density 0.104%

    No Known Activations